CVE-2026-45023: CWE-770: Allocation of Resources Without Limits or Throttling in Significant-Gravitas AutoGPT
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.59, POST /api/blocks/{block_id}/execute endpoint executes blocks without consuming any credits, regardless of the user's balance. The credit check that exists in the graph execution path (manager.py) is never reached when blocks are called directly via the external API, allowing unlimited free execution of all blocks. This vulnerability is fixed in 0.6.59.
AI Analysis
Technical Summary
AutoGPT is a platform for managing AI agent workflows. Before version 0.6.59, the POST /api/blocks/{block_id}/execute endpoint did not enforce credit consumption checks when executing blocks directly through the external API. The credit validation logic present in the graph execution path (manager.py) was bypassed, allowing users to execute blocks without decrementing their credit balance. This constitutes an allocation of resources without limits or throttling (CWE-770). The issue was resolved in version 0.6.59.
Potential Impact
The vulnerability allows users with at least limited privileges (PR:L) to execute blocks repeatedly without consuming credits, which can lead to denial of service through resource exhaustion. There is no direct confidentiality impact, but integrity and availability are affected due to the potential for abuse of the execution resource.
Mitigation Recommendations
Upgrade AutoGPT to version 0.6.59 or later, where this vulnerability is fixed. Since the vendor has released a fixed version, applying this official update is the recommended remediation. Patch status is confirmed by the vendor's versioning information. No additional mitigations are specified.
CVE-2026-45023: CWE-770: Allocation of Resources Without Limits or Throttling in Significant-Gravitas AutoGPT
Description
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.59, POST /api/blocks/{block_id}/execute endpoint executes blocks without consuming any credits, regardless of the user's balance. The credit check that exists in the graph execution path (manager.py) is never reached when blocks are called directly via the external API, allowing unlimited free execution of all blocks. This vulnerability is fixed in 0.6.59.
CVSS v3.1
Score 5.4medium
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
AutoGPT is a platform for managing AI agent workflows. Before version 0.6.59, the POST /api/blocks/{block_id}/execute endpoint did not enforce credit consumption checks when executing blocks directly through the external API. The credit validation logic present in the graph execution path (manager.py) was bypassed, allowing users to execute blocks without decrementing their credit balance. This constitutes an allocation of resources without limits or throttling (CWE-770). The issue was resolved in version 0.6.59.
Potential Impact
The vulnerability allows users with at least limited privileges (PR:L) to execute blocks repeatedly without consuming credits, which can lead to denial of service through resource exhaustion. There is no direct confidentiality impact, but integrity and availability are affected due to the potential for abuse of the execution resource.
Mitigation Recommendations
Upgrade AutoGPT to version 0.6.59 or later, where this vulnerability is fixed. Since the vendor has released a fixed version, applying this official update is the recommended remediation. Patch status is confirmed by the vendor's versioning information. No additional mitigations are specified.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-05-08T16:58:28.896Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a18bf3ae29bf47b50390f25
Added to database: 5/28/2026, 10:18:34 PM
Last enriched: 5/28/2026, 10:34:32 PM
Last updated: 5/29/2026, 6:28:42 PM
Views: 8
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.